<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2021-beyond">
    <titleInfo>
        <title>Beyond Sentence-Level End-to-End Speech Translation: Context Helps</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Biao</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ivan</namePart>
        <namePart type="family">Titov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Barry</namePart>
        <namePart type="family">Haddow</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Rico</namePart>
        <namePart type="family">Sennrich</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-aug</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Document-level contextual information has shown benefits to text-based machine translation, but whether and how context helps end-to-end (E2E) speech translation (ST) is still under-studied. We fill this gap through extensive experiments using a simple concatenation-based context-aware ST model, paired with adaptive feature selection on speech encodings for computational efficiency. We investigate several decoding approaches, and introduce in-model ensemble decoding which jointly performs document- and sentence-level translation using the same model. Our results on the MuST-C benchmark with Transformer demonstrate the effectiveness of context to E2E ST. Compared to sentence-level ST, context-aware ST obtains better translation quality (+0.18-2.61 BLEU), improves pronoun and homophone translation, shows better robustness to (artificial) audio segmentation errors, and reduces latency and flicker to deliver higher quality for simultaneous translation.</abstract>
    <identifier type="citekey">zhang-etal-2021-beyond</identifier>
    <identifier type="doi">10.18653/v1/2021.acl-long.200</identifier>
    <location>
        <url>https://aclanthology.org/2021.acl-long.200</url>
    </location>
    <part>
        <date>2021-aug</date>
        <extent unit="page">
            <start>2566</start>
            <end>2578</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Beyond Sentence-Level End-to-End Speech Translation: Context Helps
%A Zhang, Biao
%A Titov, Ivan
%A Haddow, Barry
%A Sennrich, Rico
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 aug
%I Association for Computational Linguistics
%C Online
%F zhang-etal-2021-beyond
%X Document-level contextual information has shown benefits to text-based machine translation, but whether and how context helps end-to-end (E2E) speech translation (ST) is still under-studied. We fill this gap through extensive experiments using a simple concatenation-based context-aware ST model, paired with adaptive feature selection on speech encodings for computational efficiency. We investigate several decoding approaches, and introduce in-model ensemble decoding which jointly performs document- and sentence-level translation using the same model. Our results on the MuST-C benchmark with Transformer demonstrate the effectiveness of context to E2E ST. Compared to sentence-level ST, context-aware ST obtains better translation quality (+0.18-2.61 BLEU), improves pronoun and homophone translation, shows better robustness to (artificial) audio segmentation errors, and reduces latency and flicker to deliver higher quality for simultaneous translation.
%R 10.18653/v1/2021.acl-long.200
%U https://aclanthology.org/2021.acl-long.200
%U https://doi.org/10.18653/v1/2021.acl-long.200
%P 2566-2578

Markdown (Informal)

[Beyond Sentence-Level End-to-End Speech Translation: Context Helps](https://aclanthology.org/2021.acl-long.200) (Zhang et al., ACL 2021)

• Beyond Sentence-Level End-to-End Speech Translation: Context Helps (Zhang et al., ACL 2021)

ACL

• Biao Zhang, Ivan Titov, Barry Haddow, and Rico Sennrich. 2021. Beyond Sentence-Level End-to-End Speech Translation: Context Helps. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 2566–2578, Online. Association for Computational Linguistics.